AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Scalable Trajectory Generation for Whole-Body Mobile Manipulation

Yida Niu, Xinhai Chang, Xin Liu, Ziyuan Jiao, Yixin Zhu

CVPR 2026 · Reinforcement learning › Visual and representation RL · approach: Dexterous manipulation transfer · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace CPU-based AKR planning with GPU-accelerated batched trajectory optimizationAKR planner · Trajectory generation throughputepisodes per hour: 60 -> 5,000 per hour (over 80x faster)Improved
use a mobile base instead of a fixed base (ablation)DP3 policy, single scene · Microwave door openingsuccess rate (%): 100 (fixed, <800 traj) vs about 70 (mobile, 3,200 traj)Hurt
increase number of training scenes from 1 to 30 (ablation)DP3 policy · Unseen-scene door openingsuccess rate (%)Improved
increase per-scene trajectory density with 30 scenes (ablation)DP3 policy · Seen and unseen scenes door openingsuccess rate (%): about 75% success at high densityImproved
add more demonstrations within a single scene (ablation)DP3 policy · Unseen IK start states, same scenesuccess rate (%)Mixed
train DP and ACT instead of DP3 on the same data (ablation)AutoMoMa data · 30-scene door openingsuccess rate (%)Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy